Although there are many papers on variable selection methods based on mean model in the nite mixture of regression models,little work has been done on how to select signi cant explanatory variables in the modeling of ...Although there are many papers on variable selection methods based on mean model in the nite mixture of regression models,little work has been done on how to select signi cant explanatory variables in the modeling of the variance parameter.In this paper,we propose and study a novel class of models:a skew-normal mixture of joint location and scale models to analyze the heteroscedastic skew-normal data coming from a heterogeneous population.The problem of variable selection for the proposed models is considered.In particular,a modi ed Expectation-Maximization(EM)algorithm for estimating the model parameters is developed.The consistency and the oracle property of the penalized estimators is established.Simulation studies are conducted to investigate the nite sample performance of the proposed methodolo-gies.An example is illustrated by the proposed methodologies.展开更多
Since rail-road transport uses road and rail networks and requires the transshipment infrastructures at the terminals, its competitiveness depends not only on the costs but also on the location of these terminals. Thi...Since rail-road transport uses road and rail networks and requires the transshipment infrastructures at the terminals, its competitiveness depends not only on the costs but also on the location of these terminals. This paper focused on providing a methodology for determining the optimal locations for intermodal freight transportation terminals in consolidation network. The goal is to minimize total costs in order to increase the efficiency of the transportation system. This paper also has allowed us to have an overview of the methods and models that exist for solving the problem of intermodal and terminal locating.展开更多
Variable selection is an important research topic in modern statistics, traditional variable selection methods can only select the mean model and(or) the variance model, and cannot be used to select the joint mean, va...Variable selection is an important research topic in modern statistics, traditional variable selection methods can only select the mean model and(or) the variance model, and cannot be used to select the joint mean, variance and skewness models. In this paper, the authors propose the joint location, scale and skewness models when the data set under consideration involves asymmetric outcomes,and consider the problem of variable selection for our proposed models. Based on an efficient unified penalized likelihood method, the consistency and the oracle property of the penalized estimators are established. The authors develop the variable selection procedure for the proposed joint models, which can efficiently simultaneously estimate and select important variables in location model, scale model and skewness model. Simulation studies and body mass index data analysis are presented to illustrate the proposed methods.展开更多
Path computation elements （PCEs） are employed to compute end-to-end paths across multi-domain optical networks due to the advantages of powerful computation capability. However, PCEs＇ location selection is still an...Path computation elements （PCEs） are employed to compute end-to-end paths across multi-domain optical networks due to the advantages of powerful computation capability. However, PCEs＇ location selection is still an open problem which is closely related to the communication overhead. This paper mainly focuses on the problem of PCEs＇ location selection to minimize the overall communication overhead in the control plane. The problem is formulated as a quadratic integer programming （QIP） model, and an optimal decision rule is gained from the solution of the QIP model. Then based on the decision rule, a distributed heuristic algorithm is proposed for dynamic network scenario. Simulation results demonstrate the benefit and the effectiveness of our proposed approach by comparing it with random selection policy.展开更多
基金Supported by the National Natural Science Foundation of China(11861041).
文摘Although there are many papers on variable selection methods based on mean model in the nite mixture of regression models,little work has been done on how to select signi cant explanatory variables in the modeling of the variance parameter.In this paper,we propose and study a novel class of models:a skew-normal mixture of joint location and scale models to analyze the heteroscedastic skew-normal data coming from a heterogeneous population.The problem of variable selection for the proposed models is considered.In particular,a modi ed Expectation-Maximization(EM)algorithm for estimating the model parameters is developed.The consistency and the oracle property of the penalized estimators is established.Simulation studies are conducted to investigate the nite sample performance of the proposed methodolo-gies.An example is illustrated by the proposed methodologies.
文摘Since rail-road transport uses road and rail networks and requires the transshipment infrastructures at the terminals, its competitiveness depends not only on the costs but also on the location of these terminals. This paper focused on providing a methodology for determining the optimal locations for intermodal freight transportation terminals in consolidation network. The goal is to minimize total costs in order to increase the efficiency of the transportation system. This paper also has allowed us to have an overview of the methods and models that exist for solving the problem of intermodal and terminal locating.
基金supported by the National Natural Science Foundation of China under Grant Nos.11261025,11561075the Natural Science Foundation of Yunnan Province under Grant No.2016FB005the Program for Middle-aged Backbone Teacher,Yunnan University
文摘Variable selection is an important research topic in modern statistics, traditional variable selection methods can only select the mean model and(or) the variance model, and cannot be used to select the joint mean, variance and skewness models. In this paper, the authors propose the joint location, scale and skewness models when the data set under consideration involves asymmetric outcomes,and consider the problem of variable selection for our proposed models. Based on an efficient unified penalized likelihood method, the consistency and the oracle property of the penalized estimators are established. The authors develop the variable selection procedure for the proposed joint models, which can efficiently simultaneously estimate and select important variables in location model, scale model and skewness model. Simulation studies and body mass index data analysis are presented to illustrate the proposed methods.
基金supported by the National Basic Research Program of China (2010CB328202, 2010CB328204, and 2012CB315604)the Hi-Tech Research and Development Program of China (2012AA011302)+3 种基金the Beijing Nova Program (2011065)the RFDP Project (20120005120019)the Fundamental Research Funds for the Central Universities (2013RC1201)the Fund of State Key Laboratory of Information Photonics and Optical Communications (BUPT)
文摘Path computation elements （PCEs） are employed to compute end-to-end paths across multi-domain optical networks due to the advantages of powerful computation capability. However, PCEs＇ location selection is still an open problem which is closely related to the communication overhead. This paper mainly focuses on the problem of PCEs＇ location selection to minimize the overall communication overhead in the control plane. The problem is formulated as a quadratic integer programming （QIP） model, and an optimal decision rule is gained from the solution of the QIP model. Then based on the decision rule, a distributed heuristic algorithm is proposed for dynamic network scenario. Simulation results demonstrate the benefit and the effectiveness of our proposed approach by comparing it with random selection policy.
